Recommender systems are intrinsically tied to a reliability/coverage dilemma: The more reliable we desire the forecasts, the more conservative the decision will be and thus, the fewer items will be recommended. This causes a detriment to the predictive capability of the system, as it is only able to estimate potential interest in items for which there is a consensus in their evaluation, rather than being able to estimate potential interest in any item. In this paper, we propose the inclusion of a new term in the learning process of matrix factorization-based recommender systems, called recklessness, that takes into account the variance of the output probability distribution of the predicted ratings. In this way, gauging this recklessness measure we can force more spiky output distribution, enabling the control of the risk level desired when making decisions about the reliability of a prediction. Experimental results demonstrate that recklessness not only allows for risk regulation but also improves the quantity and quality of predictions provided by the recommender system.

The explanation of and justification for recommendation results are important objectives in recommender systems because such explanations and justifications strongly influence the user's trust in the system. Traditional justification methods are based on textual explanations, which can be inadequate for analysis, comprehension, and decision making on the part of the user. In this paper, we present a method that generates tree graphs that contain the following information: the recommended items, the items that have appeared most often in the recommendation process, the relative importance of the items, and the relationships that exist among the items. The trees obtained in the experiments show (1) the greater novelty of user-to-user results, (2) the overspecialization inherent in the item-to-item approach, and (3) the equilibrium obtained by employing hybrid user-to-user/item-to-item collaborative filtering. The proposed method presents the possibility of extending recommendation result justifications to groups of users and facilitates the explanation of large numbers of recommended items.

Collaborative filtering recommender systems contribute to alleviating the problem of information overload that exists on the Internet as a result of the mass use of Web 2.0 applications. The use of an adequate similarity measure becomes a determining factor in the quality of the prediction and recommendation results of the recommender system, as well as in its performance. In this paper, we present a memory-based collaborative filtering similarity measure that provides extremely high-quality and balanced results; these results are complemented with a low processing time (high performance), similar to the one required to execute traditional similarity metrics. The experiments have been carried out on the MovieLens and Netflix databases, using a representative set of information retrieval quality measures. © 2012 Wiley Periodicals, Inc.